8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

LP-TRAP: Linear Predictive Temporal Patterns

Marios Athineos (1), Hynek Hermansky (2), Daniel P.W. Ellis (1)

(1) Columbia University, USA
(2) IDIAP, Switzerland

Auto-regressive modeling is applied for approximating the temporal evolution of spectral density in critical-band-sized sub-bands of a segment of speech signal. The generalized auto-correlation linear predictive technique allows for a compromise between fitting the peaks and the troughs of the Hilbert envelope of the signal in the sub-band. The cosine transform coefficients of the approximated sub-band envelopes, computed recursively from the all-pole polynomials, are used as inputs to a TRAP-based speech recognition system and are shown to improve recognition accuracy.

Full Paper

Bibliographic reference.  Athineos, Marios / Hermansky, Hynek / Ellis, Daniel P.W. (2004): "LP-TRAP: linear predictive temporal patterns", In INTERSPEECH-2004, 949-952.